Optimized video review using motion recap images

Abstract

Systems and methods provide for optimizing video review using motion recap images. A video review system can identify background image data of a video clip including an amount of motion satisfying a motion threshold. The video review system can generate foreground mask data segmenting foreground image data, representing a moving object in the video clip, from the background image data. The video review system can select a set of instances of the moving object represented in the foreground image data. The video review system can generate a motion recap image by superimposing the set of instances of the moving object represented in the foreground image data onto the background data.

The invention claimed is: 
     
       1. A method comprising:
 detecting one or more motions in a video feed; 
 generating motion vectors describing each of the one or more motions; 
 associating the motion vectors with one or more blocks of pixels of one or more frames of the video feed; 
 receiving a query; 
 identifying, from the motion vectors, at least a portion of the video feed that includes a motion of the one or more motions corresponding to the query; and 
 generating a motion recap image of the motion based at least in part on the motion vectors. 
 
     
     
       2. The method of  claim 1 , wherein the video feed includes at least a plurality of frames of a predefined pixel area. 
     
     
       3. The method of  claim 2 , further comprising: partitioning the plurality of frames into a plurality of blocks of pixels. 
     
     
       4. The method of  claim 3 , wherein each motion of the one or more motions is associated with at least one block of pixels of the plurality of blocks of pixels. 
     
     
       5. The method of  claim 3 , wherein each block of pixels of the plurality of blocks of pixels includes a subset of the predefined pixel area of a corresponding frame of the plurality of frames. 
     
     
       6. The method of  claim 3 , wherein the motion vectors are associated with the one or more blocks of pixels of the plurality of blocks of pixels that correspond with at least one of the one or more motions that occurred across one or more frames of the plurality of frames. 
     
     
       7. The method of  claim 2 , wherein the portion of the video feed includes at least one of the plurality of frames. 
     
     
       8. The method of  claim 2 , wherein the query includes at least a portion of the predefined pixel area. 
     
     
       9. The method of  claim 8 , the identifying further comprising:
 searching at least one of the motion vectors at the predefined pixel area for one or more frames of the video feed and block pairs that include a motion of the one or more motions corresponding to the query. 
 
     
     
       10. The method of  claim 1 , wherein generating the motion recap image includes:
 identifying background image data of the portion of the video feed; 
 generating foreground mask data by segmenting foreground image data from the background image data; and 
 selecting a set of instances of the one or more motions from the foreground image data. 
 
     
     
       11. The method of  claim 10 , wherein the foreground image data represents the one or more motions. 
     
     
       12. The method of  claim 10 , wherein the motion recap image is generated by superimposing the set of instances of the one or more motions onto the background image data. 
     
     
       13. A system comprising:
 at least one processor; and 
 a memory storing instructions, which when executed by the at least one processor, causes the at least one processor to:
 detect one or more motions in a video feed; 
 generate motion vectors describing each of the one or more motions; 
 associate the motion vectors with one or more blocks of pixels of one or more frames of the video feed; 
 receive a query; 
 identify, from the motion vectors, at least a portion of the video feed that includes a motion of the one or more motions corresponding to the query; and 
 generate a motion recap image of the motion based at least in part on the motion vectors. 
 
 
     
     
       14. The system of  claim 13 , wherein the video feed includes at least a plurality of frames of a predefined pixel area. 
     
     
       15. The system of  claim 14 , wherein the motion vectors are associated with the one or more blocks of pixels that correspond with at least one of the one or more motions that occurred across one or more frames of the video feed. 
     
     
       16. The system of  claim 15 , further comprising instructions, which when executed by the at least one processor, causes the at least one processor to:
 search at least one of the motion vectors at the predefined pixel area for one or more frames of the video feed and block pairs that include a motion of the one or more motions corresponding to the query. 
 
     
     
       17. The system of  claim 13 , further comprising instructions, which when executed by the at least one processor, causes the at least one processor to generate the motion recap image by:
 identify background image data of the portion of the video feed; 
 generate foreground mask data by segmenting foreground image data from the background image data; and 
 select a set of instances of the one or more motions from the foreground image data. 
 
     
     
       18. At least one non-transitory computer readable medium storing instructions, which when executed by at least one processor, causes the at least one processor to:
 detect one or more motions in a video feed; 
 generate motion vectors describing each of the one or more motions; 
 associate the motion vectors with one or more blocks of pixels of one or more frames of the video feed; 
 receive a query; 
 identify, from the motion vectors, at least a portion of the video feed that includes a motion of the one or more motions corresponding to the query; and 
 generate a motion recap image of the motion based at least in part on the metadata. 
 
     
     
       19. The at least one non-transitory computer readable medium of  claim 18 , wherein the motion vectors are associated with the one or more blocks of pixels that correspond with at least one of the one or more motions that occurred across one or more frames of the video feed. 
     
     
       20. The at least one non-transitory computer readable medium of  claim 18 , further comprising instructions, which when executed by the at least one processor, causes the at least one processor to generate the motion recap image by:
 identify background image data of the portion of the video feed; 
 generate foreground mask data by segmenting foreground image data from the background image data; and 
 select a set of instances of the one or more motions from the foreground image data.